WO2022246663A1 - Procédé, dispositif et système de traitement d'image, et support d'enregistrement - Google Patents

Procédé, dispositif et système de traitement d'image, et support d'enregistrement Download PDF

Info

Publication number
WO2022246663A1
WO2022246663A1 PCT/CN2021/095871 CN2021095871W WO2022246663A1 WO 2022246663 A1 WO2022246663 A1 WO 2022246663A1 CN 2021095871 W CN2021095871 W CN 2021095871W WO 2022246663 A1 WO2022246663 A1 WO 2022246663A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
histogram
image block
flat area
block
Prior art date
Application number
PCT/CN2021/095871
Other languages
English (en)
Chinese (zh)
Inventor
席迎来
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2021/095871 priority Critical patent/WO2022246663A1/fr
Publication of WO2022246663A1 publication Critical patent/WO2022246663A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration using histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows

Definitions

  • the present application relates to the technical field of image processing, and in particular to an image processing method, device, system and storage medium.
  • image and video content tends to be popularized, and users' demands for editing images and videos are increasing day by day.
  • Image/video editors have become a popular software APP on mobile terminals, providing personalized tools for image/video lovers to freely edit. Due to the variety of image/video material acquisition devices and shooting environments are also very different, usually the visual effect of image/video material cannot be 100% satisfactory, and basic quality such as lighting, contrast, color temperature, and saturation need to be adjusted.
  • the present application provides an image processing method, device, system and storage medium, aiming to solve technical problems such as image distortion easily caused by existing image/video adjustment methods.
  • the embodiment of the present application provides an image processing method, including:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the target image of each image block in the flat area is acquired according to the histogram of the flat area.
  • the determining the flat area in the image to be processed includes:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • the calculating the histogram of the flat area includes:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the acquiring the target image of each image block in the flat area according to the histogram of the flat area includes:
  • the target image of each image block in the flat area is acquired.
  • the determining the histogram of each image block in the flat area according to the histogram of the flat area includes:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the determining the histogram of each image block in the flat area according to the histogram of the flat area includes:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • the method also includes:
  • the target image of each image block outside the flat area is acquired.
  • acquiring the target image of the image block according to the histogram of the image block includes:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • the method also includes:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the determining the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of pixel values in the image block includes:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • the method also includes:
  • the smoothing the clipping threshold corresponding to the histogram of the adjacent image block includes:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • performing clipping processing on the histogram according to the clipping threshold corresponding to the histogram of the image block includes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the determining the target image of the image block according to the mapping function corresponding to the image block includes:
  • Interpolation processing is performed on the preset number of pixel values to obtain the equalized pixel values of the non-central pixels.
  • the acquisition of images to be processed includes:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • the embodiment of the present application provides an image processing device, including one or more processors, working individually or jointly, for performing the following steps:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the target image of each image block in the flat area is acquired according to the histogram of the flat area.
  • the processor executes the determining the flat area in the image to be processed, it is configured to:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • the processor executes the calculation of the histogram of the flat area, it is used to execute:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the processor executes the step of obtaining the target image of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the target image of each image block in the flat area is acquired.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • the processor is also used for:
  • the target image of each image block outside the flat area is acquired.
  • the processor acquires the target image of the image block according to the histogram of the image block, it is configured to:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • the processor is also used for:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the processor executes determining the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of the pixel values in the image block, it is used to execute:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • the processor is also used for:
  • the processor executes the smoothing processing on the clipping thresholds corresponding to the histograms of adjacent image blocks, it is used to execute:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • the processor executes the clipping threshold corresponding to the histogram of the image block, and when clipping the histogram, executes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the processor executes the mapping function corresponding to the image block to determine the target image of the image block, it is used to execute:
  • Interpolation processing is performed on the preset number of pixel values to obtain the equalized pixel values of the non-central pixels.
  • the processor executes the acquisition of the image to be processed, it is used to execute:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • the embodiment of the present application provides a terminal device, which is characterized in that it includes one or more processors, working individually or jointly, to perform the following steps:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the target image of each image block in the flat area is acquired according to the histogram of the flat area.
  • the processor executes the determining the flat area in the image to be processed, it is configured to:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • the processor executes the calculation of the histogram of the flat area, it is used to execute:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the processor executes the acquisition of the target image of each image block in the flat area according to the histogram of the flat area, it is used to execute:
  • the target image of each image block in the flat area is acquired.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • the processor is also used for:
  • the target image of each image block outside the flat area is acquired.
  • the processor acquires the target image of the image block according to the histogram of the image block, it is configured to:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • the processor is also used for:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the processor executes determining the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of the pixel values in the image block, it is used to execute:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • the processor is also used for:
  • the processor executes the smoothing processing on the clipping thresholds corresponding to the histograms of adjacent image blocks, it is used to execute:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • the processor executes the clipping threshold corresponding to the histogram of the image block, and when clipping the histogram, executes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the processor executes the mapping function corresponding to the image block to determine the target image of the image block, it is used to execute:
  • Interpolation processing is performed on the preset number of pixel values to obtain the pixel values after equalization processing of the non-central pixels.
  • the processor executes the acquisition of the image to be processed, it is used to execute:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • the embodiment of the present application provides a movable platform, the movable platform is equipped with a photographing device, and the photographing device is used to acquire images;
  • processors working individually or jointly, for performing the following steps:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the target image of each image block in the flat area is acquired according to the histogram of the flat area.
  • the processor executes the determining the flat area in the image to be processed, it is configured to:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • the processor executes the calculation of the histogram of the flat area, it is used to execute:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the processor executes the step of obtaining the target image of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the target image of each image block in the flat area is acquired.
  • the processor executes the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is used to execute:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • the processor is also used for:
  • the target image of each image block outside the flat area is acquired.
  • the processor acquires the target image of the image block according to the histogram of the image block, it is configured to:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • the processor is also used for:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the processor executes determining the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of the pixel values in the image block, it is used to execute:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • the processor is also used for:
  • the processor executes the smoothing processing on the clipping thresholds corresponding to the histograms of adjacent image blocks, it is used to execute:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • the processor executes the clipping threshold corresponding to the histogram of the image block, and when clipping the histogram, executes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the processor executes the mapping function corresponding to the image block to determine the target image of the image block, it is used to execute:
  • Interpolation processing is performed on the preset number of pixel values to obtain the equalized pixel values of the non-central pixels.
  • the processor executes the acquisition of the image to be processed, it is used to execute:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • the embodiment of the present application provides an image processing system, including a shooting device and a display device, and also includes one or more processors, working individually or jointly, for performing the following steps to process the shooting
  • the image acquired by the device is processed by:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the display device can display the image processed by the processor.
  • the processor executes the determining the flat area in the image to be processed, it is configured to:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • the processor executes the calculation of the histogram of the flat area, it is used to execute:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the processor executes the step of obtaining the target image of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the target image of each image block in the flat area is acquired.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the processor when the processor performs the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • the processor is also used for:
  • the target image of each image block outside the flat area is acquired.
  • the processor acquires the target image of the image block according to the histogram of the image block, it is configured to:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • the processor is also used for:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the processor executes determining the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of the pixel values in the image block, it is used to execute:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • the processor is also used for:
  • the processor executes the smoothing processing on the clipping thresholds corresponding to the histograms of adjacent image blocks, it is used to execute:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • the processor executes the clipping threshold corresponding to the histogram of the image block, and when clipping the histogram, executes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the processor executes the mapping function corresponding to the image block to determine the target image of the image block, it is used to execute:
  • Interpolation processing is performed on the preset number of pixel values to obtain the equalized pixel values of the non-central pixels.
  • the processor executes the acquisition of the image to be processed, it is used to execute:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • the embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the above method.
  • Embodiments of the present application provide an image processing method, device, system, and storage medium, by using adjacent image blocks whose sum of information entropy is less than or equal to a preset threshold as a class, that is, a flat area, to realize image processing in an image Blocks are classified more intelligently to prevent different objects from being divided into the same area, and then according to the histogram of the flat area, such image blocks with certain similarities are processed, and the image blocks in the flat area are stretched more evenly , to prevent distortion, can reduce image distortion, and the processing effect is better.
  • a preset threshold as a class
  • FIG. 1 is a schematic flow diagram of an image processing method provided in an embodiment of the present application
  • Fig. 2 is a schematic diagram of an application scene of an image processing method in an embodiment
  • Fig. 3 is a schematic diagram of dividing an image to be processed into a plurality of image blocks in an embodiment
  • Fig. 4 is a schematic diagram of a flat area in an image to be processed in an embodiment
  • Fig. 5 is a schematic diagram of an image to be processed in an embodiment
  • Fig. 6 is a schematic diagram of an image to be processed after image processing in one embodiment
  • Fig. 7 is a schematic diagram of a processed image of an image to be processed in another embodiment
  • Fig. 8 is a schematic diagram of clipping a histogram in an embodiment
  • Fig. 9 is a schematic diagram of clipping thresholds corresponding to different image blocks in an embodiment
  • Fig. 10 is a schematic diagram of image blocks adjacent to different pixels in an embodiment
  • Fig. 11 is a schematic block diagram of an image processing device provided by an embodiment of the present application.
  • Fig. 12 is a schematic block diagram of a mobile platform provided by an embodiment of the present application.
  • Fig. 13 is a schematic block diagram of an image processing system provided by an embodiment of the present application.
  • Fig. 14 is a schematic block diagram of a terminal device provided by an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of an image processing method provided in an embodiment of the present application.
  • the image processing method can be applied in an image processing device or an image processing system, and is used for processing an image according to a histogram of the image, and the like.
  • the image processing equipment includes, for example, at least one of an image signal processor (Image Signal Processor, ISP), a digital signal processor (Digital Signal Processor, DSP), and an application processor (Application Processor, AP), and of course it is not limited to Therefore, for example, a SoC (System on Chip, System on Chip) chip may be included.
  • an image signal processor Image Signal Processor, ISP
  • a digital signal processor Digital Signal Processor, DSP
  • AP Application Processor
  • SoC System on Chip, System on Chip
  • the image processing device may or may not include an image sensor.
  • the image processing system includes, for example, at least one of a terminal device, a mobile platform, and a server.
  • a terminal device may include at least one of a mobile phone, a camera, a video camera, a tablet computer, a notebook computer, a personal digital assistant, a wearable device, a remote control, etc.; At least one of people and vehicles.
  • the unmanned aerial vehicle may be a rotor-type drone, such as a quad-rotor drone, a hexacopter drone, an octo-rotor drone, or a fixed-wing drone.
  • the server may be an individual server, or may be a server cluster.
  • the camera device 110 carried by the movable platform 100 acquires images in real time, and processes the images according to the image processing method; terminal device 200.
  • the terminal device 200 may be, for example, a mobile phone, a computer, FPV (First Person View, first-person perspective) glasses, and the like.
  • the display device 210 included in the terminal device 200 can display images received from the mobile platform 100 for viewing by the user.
  • the camera device 110 mounted on the mobile platform 100 acquires images in real time, and sends the acquired images to the terminal device 200 communicatively connected to the mobile platform 100 .
  • the terminal device 200 processes the image received from the mobile platform 100 according to the image processing method, and can also display the processed image for the user to watch.
  • the terminal device acquires images through the equipped camera, or acquires locally stored images, or acquires images from the server, and processes the acquired images according to the image processing method, and can also display the processed images, for users to view.
  • the image processing method of the embodiment of the present application includes step S110 to step S130.
  • the image to be processed can be stored locally, or collected in real time by the camera, or obtained from other devices through a communication link, and the image to be processed can be an independent image or a video stream
  • the images in are not limited to this.
  • the acquiring the image to be processed includes: acquiring the image to be processed in the HSL (Hue, Saturation, Lightness) domain or HSV (Hue, Saturation, Value, hue, saturation, lightness) The pending image for the domain.
  • HSL Human, Saturation, Lightness
  • HSV Human, Saturation, Value, hue, saturation, lightness
  • the image to be processed can be RGB (Red, Green, Blue, red, green, blue) domain, CMY/CMYK (Cyan, Magenta, Yellow, Black, cyan, magenta, yellow, black) domain, Lab (Lightness means brightness, a is from dark green (low brightness value) to gray (medium brightness value) to bright pink (high brightness value), b is from bright blue (low brightness value) to gray (medium brightness value) ) to yellow (high brightness value)) domain or YUV/YCbCr (Y represents brightness, U represents chroma, V represents density, Cb represents the degree of offset to blue, Cr represents the degree of offset to red) domain image.
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • the image processing method may process the saturation component of the image to be processed, or the image processing method may process the saturation component of the image to be processed, or the image processing method may Process the saturation component and brightness component of the image to be processed.
  • the brightness component may be the brightness (Lightness) component of the image to be processed in the HSL domain, or may be the value (Value) component of the image to be processed in the HSV domain, and of course it is not limited thereto.
  • the image to be processed is converted into an image to be processed in the HSL domain or an image to be processed in the HSV domain, and then at least one component is processed; after the processing is completed, it can also be converted to the original color space (domain) Image.
  • converting the image to be processed to the HSL domain and processing the brightness and saturation components can ensure that the contrast and color of the image are well stretched, corrected to an appropriate range, and avoid the RGB domain histogram Chromatic aberration caused by equalization.
  • the image to be processed is divided into multiple image blocks with multiple rows and multiple columns, for example, 8 rows and 8 columns with 64 image blocks in total, as shown in FIG. 3 .
  • the sizes of the divided image blocks are all the same, that is, the image to be processed is evenly divided into a plurality of image blocks.
  • the image to be processed can be extended horizontally to an integer multiple of the number of columns, if the width of the image to be processed cannot be divided by the preset If the number of rows of the image block is evenly divided, the image to be processed can be extended to an integer multiple of the number of rows in the vertical direction.
  • the sizes of the multiple divided image blocks may also be different, for example, the sizes of the multiple divided image blocks may be determined according to the composition of the image to be processed.
  • the object distances corresponding to the pixels in the flat area are approximately the same.
  • the flat area in the image to be processed may include sky, water, road, wall, etc.
  • the flat area is, for example, a background area.
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, and all the image blocks in the flat area
  • the sum of the information entropies of the image blocks is less than or equal to the preset threshold.
  • the image blocks in the image are classified more intelligently, and the adjacent image blocks whose sum of information entropy is less than or equal to the preset threshold are regarded as a class, that is, the flat area, and the image blocks in the same flat area have similarity, grayscale Image characteristics such as color, texture, etc. have no or small mutations, such as the grayscale of each pixel in an image block in the same flat area is in the same or similar grayscale range. It can prevent image blocks with different image properties from being divided into one flat area, thereby preventing distortion phenomena such as distortion between areas with different image properties in the processed image.
  • the information entropy of an image is a statistical form of a feature, which reflects the average amount of information in the image.
  • the information entropy of the image block can be one-dimensional entropy or two-dimensional entropy, wherein the one-dimensional entropy represents the amount of information contained in the aggregation characteristics of the grayscale distribution of the image block, based on the one-dimensional entropy
  • the two-dimensional entropy of the image block can be obtained by introducing a feature quantity that can reflect the spatial characteristics of the gray distribution.
  • each image block in the image to be processed determines the information entropy of each image block; if the sum of the information entropy of at least two adjacent image blocks is less than or equal to the preset threshold , determining that the at least two adjacent image blocks are located in the same flat area.
  • a preset component of each image block is calculated, such as a histogram of a brightness component, and information entropy of each image block is determined according to the histogram.
  • the information entropy H of the image block is determined according to the following formula:
  • 0 to 255 is the range of the preset component, and of course it is not limited thereto, i represents any value within the range, p i is the probability that the value i within the range appears in the image block , p i can be determined according to the histogram of the image block.
  • multiple adjacent image blocks can be combined to obtain the flat area, for example, if the sum of the information entropy of adjacent image blocks is less than or equal to the preset threshold, then These image blocks can be merged, if the sum of the information entropy of these image blocks and the information entropy of adjacent image blocks of these image blocks is still less than or equal to the preset threshold, then these image blocks and these image blocks Adjacent image blocks are merged until the information entropy is equal to or greater than the preset threshold, and it can be determined that the flat area is obtained from the merged image blocks.
  • Fig. 4 house, tower and sky are included in the image to be processed, it is determined that the flat area in the image to be processed includes the sky on the left side of the upper half of the tower and the sky on the right side, and the image blocks in the two sky areas are all Not adjacent, can be determined as two flat areas.
  • the image to be processed includes the wall and the sky. If the image characteristics of the wall and the sky are different, they can be divided into two flat areas. If the wall and the sky are adjacent, the two flat areas can also be adjacent. If the wall and the sky are not adjacent, then the two flat areas divided are not adjacent. Of course, if the image properties of the walls and the sky are the same and the walls and the sky are adjacent, the adjacent walls and the sky can be divided into a flat region.
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the histogram of each image block in the flat area is superimposed, and the superimposed histogram is divided by the number of image blocks in the flat area to obtain the histogram of the flat area.
  • the histogram of the image block is prone to peaks.
  • the histogram of the flat area in the embodiment of the present application can be obtained by superimposing the histograms of multiple image blocks in the flat area, which can prevent The histogram is spiked, so image processing works better based on the histogram of said flat areas.
  • each image block in the flat area is processed through histogram equalization to obtain a corresponding target image.
  • the acquiring the target image of each image block in the flat area according to the histogram of the flat area includes: determining the histogram of each image block in the flat area according to the histogram of the flat area Figure: Acquiring the target image of each image block in the flat area according to the histogram of each image block in the flat area.
  • a mapping function corresponding to the image block is determined according to the histogram of the image block in the flat area, and a target image of the image block is determined according to the mapping function corresponding to the image block.
  • the histogram of the image block is clipped, and the mapping function corresponding to the image block is determined according to the clipped histogram, and the mapping function is used to indicate the preset component of the image block and the image
  • the mapping relationship between the preset components of the target image of the block, so the target image of the image block can be determined according to the mapping function.
  • the histograms of different image blocks in the same flat area determined according to the histograms of the flat area are all the same.
  • the histogram of the flat area is used as the histogram of each image block in the flat area. It can be understood that the histogram of each image block in the flat area may be the histogram of the flat area.
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • the histogram of a single image block in a flat area tends to have peaks, and processing the image block according to the histogram of a single image block may easily cause image distortion, for example, an excessive increase in local contrast may be caused.
  • the histogram of each image block in the flat area is determined according to the histogram of the flat area, and the histogram of the entire flat area can be obtained from the histograms of multiple image blocks in the flat area The images are superimposed, so the histogram is not prone to peaks, which can reduce image distortion and improve the processing effect.
  • the method further includes: calculating a histogram of each image block outside the flat area in the image to be processed; obtaining the flat area according to the histogram of each image block outside the flat area.
  • mapping function corresponding to the image block outside the flat area can also be determined according to the histogram of each image block outside the flat area, and according to the mapping function corresponding to the image block outside the flat area , determine the target image of the image block outside the flat area.
  • the information entropy of the image blocks outside the flat area is larger, or the information entropy of adjacent image blocks is larger although the information entropy is smaller.
  • the processed image of the image to be processed can be obtained, as shown in FIG. 5
  • the image to be processed is the processed image of the image to be processed, the contrast and color of the image have been stretched in a better range, corrected to a suitable range, and the image distortion has been reduced, such as reducing localized image distortion in flat areas.
  • performing clipping processing on the histogram according to a clipping threshold corresponding to the histogram of the image block includes: determining an area in the histogram of the image block whose magnitude is higher than the clipping threshold; According to the quotient of the area and the horizontal width of the histogram, determine the rising height of the amplitude in the histogram; if the amplitude in the histogram is lower than the difference between the clipping threshold and the rising height, according to The ascent height increases the magnitude; and/or, if the magnitude in the histogram is higher than the difference between the clipping threshold and the ascent height, setting the magnitude as the clipping threshold.
  • the area in the histogram of the image block whose magnitude is higher than the clipping threshold can be uniformly distributed on the horizontal width of the histogram, and the horizontal width is determined according to the range of the preset component , to determine the rising height of the partial amplitude before the clipping process, and the rising height is used to lift the amplitude in the histogram lower than the difference between the clipping threshold and the rising height during the clipping process, so that the clipping process
  • the total area of the front and back histograms is constant, but of course it is not limited to this.
  • the clipping threshold corresponding to the histogram of the image block is expressed as ClipLimit
  • the area of the part in the histogram higher than ClipLimit is expressed as totalExcess
  • the amplitude in the histogram is greater than ClipLimit, set the amplitude directly to ClipLimit; if the amplitude in the histogram is greater than or equal to upper and less than or equal to ClipLimit, set the amplitude to ClipLimit; if the amplitude in the histogram is smaller than upper, increase the amplitude to the rising height L.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold of the histogram in Fig. 6 is smaller than the clipping threshold of the histogram in Fig. 7, when the clipping threshold is small, the contrast and The stretching of the color is not enough, and the image toning effect is not obvious enough; when the clipping threshold is large, the contrast and color stretching of the flat area of the image, such as the box in Figure 7, is excessive, and the image toning effect is somewhat abrupt, such as As shown in Figure 7, the contrast stretching to the sky is overly exaggerated. It can be seen that the size of the clipping threshold has a great influence on the effect of image processing. By determining different histogram clipping thresholds for different image blocks in the image to be processed, it can be ensured that each region in the image to be processed can be properly processed, such as contrast stretching, and the effect of image processing is better .
  • the clipping threshold corresponding to the histogram of the image block outside the flat area is greater than the clipping threshold corresponding to the histogram of the image block in the flat area, so the stretching degree of the non-flat area can be guaranteed. And image toning effect, it can also prevent the contrast and color stretching in flat areas, and ensure that each area gets the appropriate contrast stretching.
  • the method further includes: determining information entropy of the image block and/or distribution parameters of pixel values in the image block according to the histogram of the image block; Or the distribution parameters of the pixel values in the image block, and determine the clipping threshold corresponding to the histogram. Therefore, the adaptive adjustment of the clipping thresholds of different image blocks can be realized.
  • the cropping threshold is positively correlated with the information entropy of the image block, which can improve the contrast and color stretching of the image block with larger information entropy, and the effect of image toning is more obvious, and reduces the impact on image blocks with smaller information entropy.
  • the contrast and color stretching of image blocks prevents excessive stretching.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation.
  • the clipping threshold corresponding to the histogram of the image block may be adjusted according to the degree of dispersion of pixel values in the image block, and image blocks with a higher degree of dispersion may be more stretched.
  • the distribution parameter of pixel values in the image includes an average value of pixel values in the image block, and the clipping threshold is negatively correlated with the average value.
  • An image block with a lower average value of pixel values in the image block can be more stretched.
  • the quotient of the standard deviation and the mean value of the pixel values in the image block may be multiplied by a preset weight coefficient and added to the information entropy of the image block to obtain the clipping threshold corresponding to the histogram.
  • the clipping threshold ClipLimit corresponding to the histogram of the image block can be determined according to the following formula:
  • ⁇ represents the standard deviation of the pixel values in the image block
  • ⁇ represents the mean value of the pixel values in the image block
  • the quotient of ⁇ and ⁇ can be used to indicate the image dynamic range of the image block
  • ⁇ represents the preset coefficient , used to adjust the weight of the information entropy of the image block and the dynamic range of the image, for example, the value of ⁇ is 1 to 5, such as 3.
  • FIG. 9 is a schematic diagram of clipping thresholds corresponding to the histograms of different image blocks in the image to be processed, and image blocks with richer details have higher clipping thresholds.
  • the method further includes: smoothing the clipping thresholds corresponding to the histograms of adjacent image blocks.
  • the clipping thresholds corresponding to the histograms of adjacent image blocks may be smoothed by mean filtering, but of course it is not limited thereto. Prevent certain block effects in the processed image when the clipping thresholds of adjacent image blocks differ greatly.
  • the mapping function of the corresponding image block can be determined according to the clipped histogram, and the processed image of the image to be processed can be determined according to the mapping function of each image in the image to be processed.
  • the determining the target image of the image block according to the mapping function corresponding to the image block includes: determining the equalized pixel of the central pixel of the image block according to the mapping function corresponding to the image block value; determine the preset number of image blocks adjacent to the non-central pixel of the image block; determine the preset number of pixels corresponding to the non-central pixel according to the mapping function corresponding to the preset number of image blocks value; performing interpolation processing on the preset number of pixel values to obtain the equalized pixel value of the non-central pixel. Through interpolation processing, the computational load of image processing can be reduced.
  • histogram equalization can be performed on the central pixel of the image block, and the image to be processed can be determined by interpolating the mapping function of the local neighborhood of any pixel in the image to be processed The mapping function of any pixel in the image to perform histogram equalization on the remaining pixels except the central pixel of each image block.
  • the pixel value after equalization processing of the central pixel 11 of each image block is determined according to the pixel value of the central pixel 11 and the mapping function of the image block;
  • the image blocks adjacent to the non-central pixel 12 include Four, four pixel values can be determined according to the pixel values of the non-central pixel 12 and the four mapping functions corresponding to the image blocks adjacent to the non-central pixel 12, and bilinear interpolation can be performed on the four pixel values to determine
  • the non-central pixel 12 equalizes the pixel value after processing;
  • the image block adjacent to the non-central pixel 13 in the image block at the edge of the image to be processed and not in the four corners includes two, which can be based on the non-central pixel 13
  • the pixel value and the two mapping functions corresponding to the image blocks adjacent to the non-central pixel 13 determine two pixel values, and performing linear interpolation on the two pixel values can determine the equalized pixel value of the non-central pixel 13;
  • a processed image of the image to be processed can be obtained according to the target image after equalization processing of all image blocks.
  • image processing is performed on the brightness component of the image to be processed, and image processing is performed on the saturation component of the image to be processed, and the color space is changed according to the brightness component and saturation component after image processing to obtain RGB Image in color space, get exposure, contrast, color corrected image.
  • both the brightness component and the saturation component of the image to be processed are mapped to an integer in the interval [0, 255], and then histogram equalization processing is performed, and the brightness component and saturation component after the histogram equalization processing are A float renormalized to the interval [0, 1].
  • the image processing method provided by the embodiment of the present application realizes more intelligent classification of the image blocks in the image by taking the adjacent image blocks whose sum of information entropy is less than or equal to the preset threshold as a class, that is, the flat area, to prevent Divide different objects in the same area, and then process such image blocks with certain similarities according to the histogram of the flat area, stretch the image blocks in the flat area more evenly, prevent distortion, and reduce image distortion. Handling is better.
  • the image processing method can provide simple and fast intelligent image color adjustment, and can quickly generate a primary color adjustment effect with only a very simple interaction. For example, the user only needs to click the color adjustment button to directly correct the exposure and color of the screen to a normal level, realize one-click adjustment of image quality, and achieve basically satisfactory results.
  • This method can not only process images quickly, but also be suitable for real-time processing of high-definition video.
  • the exemplary image processing method can be conveniently configured on the editor APP of the mobile terminal, and can realize high-resolution video, such as real-time grading processing of 1080P video, so that users can edit images or videos as they like anytime, anywhere. Smart color editing. The interaction is simpler, the implementation is more convenient, and the flexibility is stronger, which greatly reduces the user's threshold for use.
  • FIG. 11 is a schematic block diagram of an image processing device 400 provided by an embodiment of this specification.
  • the image processing device 400 includes one or more processors 401 working individually or jointly for executing the steps of the image processing method of the foregoing embodiments.
  • the image processing device includes at least one of an image signal processor (Image Signal Processor, ISP), a digital signal processor (Digital Signal Processor, DSP), an application processor (Application Processor, AP), and of course Not limited thereto, for example, a SoC (System on Chip, System on Chip) chip may be included. It should be noted that the image processing device may or may not include an image sensor.
  • ISP Image Signal Processor
  • DSP Digital Signal Processor
  • AP Application Processor
  • SoC System on Chip, System on Chip
  • the processor 401 is used for:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the target image of each image block in the flat area is acquired according to the histogram of the flat area.
  • the processor 401 executes the determining the flat area in the image to be processed, it is configured to:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • processor 401 executes the calculation of the histogram of the flat area, it is configured to:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the processor 401 executes the acquisition of the target image of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the target image of each image block in the flat area is acquired.
  • the processor 401 executes the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the processor 401 executes the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • processor 401 is also used for:
  • the target image of each image block outside the flat area is acquired.
  • the processor 401 executes acquiring the target image of the image block according to the histogram of the image block, it is used to execute:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • processor 401 is also used for:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the processor 401 determines the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of the pixel values in the image block, it is used to execute:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • processor 401 is also used for:
  • the processor 401 executes the smoothing processing on the clipping threshold corresponding to the histogram of the adjacent image block, it is used to execute:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • the processor 401 executes the clipping threshold corresponding to the histogram of the image block, and when clipping the histogram, executes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the processor 401 executes the mapping function corresponding to the image block to determine the target image of the image block, it is used to execute:
  • Interpolation processing is performed on the preset number of pixel values to obtain the equalized pixel values of the non-central pixels.
  • processor 401 executes the acquisition of the image to be processed, it is used to execute:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • FIG. 12 is a schematic block diagram of a mobile platform 500 provided in another embodiment of this specification.
  • the mobile platform 500 may include at least one of an unmanned aerial vehicle, a cloud platform, an unmanned vehicle, and the like.
  • the unmanned aerial vehicle may be a rotor-type drone, such as a quad-rotor drone, a hexacopter drone, an octo-rotor drone, or a fixed-wing drone.
  • the photographing device 510 can be mounted on the movable platform 500 , and the photographing device 510 is used to acquire images, and the movable platform 500 can process the images acquired by the photographing device 510 .
  • the mobile platform 500 also includes one or more processors 501, and the one or more processors 501 can work individually or jointly to execute the steps of the image processing method of the foregoing embodiments.
  • the processor 501 is used for:
  • the flat area includes at least two image blocks, and in the flat area, each image block has at least one adjacent image block, The sum of the information entropies of all the image blocks in the flat area is less than or equal to a preset threshold;
  • the target image of each image block in the flat area is acquired according to the histogram of the flat area.
  • the processor 501 executes the determining the flat area in the image to be processed, it is configured to:
  • the sum of the information entropies of at least two adjacent image blocks is less than or equal to the preset threshold, it is determined that the at least two adjacent image blocks are located in the same flat area.
  • processor 501 executes the calculation of the histogram of the flat area, it is configured to:
  • the histogram of each image block in the flat area is superimposed to obtain the histogram of the flat area.
  • the processor 501 executes the acquisition of the target image of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the target image of each image block in the flat area is acquired.
  • the processor 501 executes the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is used as the histogram of each image block in the flat area.
  • the processor 501 executes the determining the histogram of each image block in the flat area according to the histogram of the flat area, it is configured to:
  • the histogram of the flat area is divided to obtain the histogram of each image block in the flat area.
  • processor 501 is also used for:
  • the target image of each image block outside the flat area is acquired.
  • the processor 501 acquires the target image of the image block according to the histogram of the image block, it is configured to:
  • the target image of the image block is determined according to the mapping function corresponding to the image block.
  • the clipping thresholds corresponding to the histograms of at least two image blocks are different.
  • the clipping threshold corresponding to the histogram of the image blocks outside the flat area is greater than the clipping threshold corresponding to the histogram of the image blocks in the flat area.
  • processor 501 is also used for:
  • a clipping threshold corresponding to the histogram is determined according to information entropy of the image block and/or a distribution parameter of pixel values in the image block.
  • the clipping threshold is positively correlated with the information entropy of the image block.
  • the distribution parameter of pixel values in the image block includes a standard deviation of pixel values in the image block, and the clipping threshold is positively correlated with the standard deviation;
  • the distribution parameters of the pixel values in the image include the mean value of the pixel values in the image block, and the clipping threshold is negatively correlated with the mean value.
  • the processor 501 executes determining the clipping threshold corresponding to the histogram according to the information entropy of the image block and/or the distribution parameters of the pixel values in the image block, it is used to execute:
  • the quotient of the standard deviation and the mean value of the pixel values in the image block is multiplied by a preset weight coefficient, and the information entropy of the image block is added to obtain the clipping threshold corresponding to the histogram.
  • processor 501 is also used for:
  • the processor 501 executes the smoothing processing on the clipping threshold corresponding to the histogram of the adjacent image block, it is used to execute:
  • the clipping thresholds corresponding to the histograms of adjacent image blocks are smoothed by mean filtering.
  • the processor 501 executes the clipping threshold corresponding to the histogram of the image block, and when clipping the histogram, executes:
  • the magnitude in the histogram is lower than the difference between the clipping threshold and the rise height, increase the magnitude according to the rise height; and/or, if the magnitude in the histogram is higher than the The difference between the clipping threshold and the rising height, and set the amplitude as the clipping threshold.
  • the processor 501 executes the mapping function corresponding to the image block to determine the target image of the image block, it is used to execute:
  • Interpolation processing is performed on the preset number of pixel values to obtain the equalized pixel values of the non-central pixels.
  • processor 501 executes the acquisition of the image to be processed, it is used to execute:
  • the image processing method processes at least one of the following components of the image to be processed: a saturation component and a brightness component.
  • FIG. 13 is a schematic block diagram of an image processing system 600 provided in another embodiment of this specification.
  • the image processing system 600 includes, for example, at least one of a terminal device, a mobile platform, and a server.
  • a terminal device may include at least one of a mobile phone, a camera, a video camera, a tablet computer, a notebook computer, a personal digital assistant, a wearable device, a remote control, etc.; At least one of people and vehicles.
  • the unmanned aerial vehicle may be a rotor-type drone, such as a quad-rotor drone, a hexacopter drone, an octo-rotor drone, or a fixed-wing drone.
  • the server may be an individual server, or may be a server cluster.
  • the image processing system 600 includes a photographing device 610 and a display device 620 , and also includes one or more processors 601 .
  • one or more processors 601 may be mounted on the camera device 610 and/or the display device 620 .
  • One or more processors 601 may work individually or jointly to execute the steps of the image processing method of the foregoing embodiments, so as to process the image acquired by the photographing device 610 .
  • the display device 620 can display the image processed by the processor 601 .
  • FIG. 14 is a schematic block diagram of a terminal device 700 provided in another embodiment of this specification.
  • the terminal device 700 may include at least one of a mobile phone, a camera, a video camera, a tablet computer, a notebook computer, a personal digital assistant, a wearable device, a remote controller, and the like.
  • the terminal device 700 includes one or more processors 701, and the one or more processors 701 can work individually or jointly to execute the steps of the image processing method of the foregoing embodiments.
  • An embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the image processing method provided in the above-mentioned embodiment step.
  • the computer-readable storage medium may be an internal storage unit of the system, device, or removable platform described in any of the foregoing embodiments, such as a hard disk or memory of the removable platform.
  • the computer-readable storage medium can also be an external storage device of the system, device or removable platform, such as a plug-in hard disk equipped on the removable platform, a smart memory card (Smart Media Card, SMC), a security Digital (Secure Digital, SD) card, flash memory card (Flash Card), etc.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

Un procédé de traitement d'image comprend les étapes consistant à : acquérir une image à traiter (S110) ; diviser ladite image en une pluralité de blocs d'image (S120) ; déterminer une zone plate dans ladite image (S130) ; calculer un histogramme de la zone plate (S140) ; et acquérir une image cible de chaque bloc d'image dans la zone plate conformément à l'histogramme de la zone plate (S150). Selon la présente demande, une image peut être traitée conformément à un histogramme de l'image. La présente invention concerne également un dispositif, un système et un support d'enregistrement.
PCT/CN2021/095871 2021-05-25 2021-05-25 Procédé, dispositif et système de traitement d'image, et support d'enregistrement WO2022246663A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/095871 WO2022246663A1 (fr) 2021-05-25 2021-05-25 Procédé, dispositif et système de traitement d'image, et support d'enregistrement

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/095871 WO2022246663A1 (fr) 2021-05-25 2021-05-25 Procédé, dispositif et système de traitement d'image, et support d'enregistrement

Publications (1)

Publication Number Publication Date
WO2022246663A1 true WO2022246663A1 (fr) 2022-12-01

Family

ID=84229301

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/095871 WO2022246663A1 (fr) 2021-05-25 2021-05-25 Procédé, dispositif et système de traitement d'image, et support d'enregistrement

Country Status (1)

Country Link
WO (1) WO2022246663A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110157247A1 (en) * 2009-12-25 2011-06-30 Hitachi Consumer Electronics Co., Ltd. Display Apparatus and Control Circuit of the Same
CN107330863A (zh) * 2017-05-27 2017-11-07 浙江大学 一种基于噪声估计的图像去噪方法
CN109003249A (zh) * 2017-06-07 2018-12-14 展讯通信(天津)有限公司 增强图像细节的方法、装置及终端
CN110807750A (zh) * 2019-11-14 2020-02-18 青岛海信电器股份有限公司 图像处理方法和设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110157247A1 (en) * 2009-12-25 2011-06-30 Hitachi Consumer Electronics Co., Ltd. Display Apparatus and Control Circuit of the Same
CN107330863A (zh) * 2017-05-27 2017-11-07 浙江大学 一种基于噪声估计的图像去噪方法
CN109003249A (zh) * 2017-06-07 2018-12-14 展讯通信(天津)有限公司 增强图像细节的方法、装置及终端
CN110807750A (zh) * 2019-11-14 2020-02-18 青岛海信电器股份有限公司 图像处理方法和设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHANG XUEDIAN, YANG FAN; CHANG MIN: "Image Enhancement Algorithm Based on Entropy Statistical Histogram of Image Information", BAOZHUANG GONGCHENG - PACKAGING ENGINEERING, ZHONGGUO BINGQI GONGYE DI-59 YANJIUSUO, CN, vol. 41, no. 13, 15 July 2020 (2020-07-15), CN , pages 251 - 260, XP093008472, ISSN: 1001-3563, DOI: 10.19554/j.cnki.1001-3563.2020.13.036 *

Similar Documents

Publication Publication Date Title
US9767544B2 (en) Scene adaptive brightness/contrast enhancement
CN106780311B (zh) 一种结合皮肤粗糙度的快速人脸图像美化方法
WO2018082185A1 (fr) Procédé et dispositif de traitement d'image
US8723982B2 (en) Image processing device, storage medium, and image processing method that corrects saturation, specific color and spatial frequency of an obtained image
US9842382B2 (en) Method and device for removing haze in single image
WO2020125631A1 (fr) Procédé et appareil de compression vidéo, et support de stockage lisible par ordinateur
JP4870617B2 (ja) 画像データの自動マッピング方法及び画像処理デバイス
CN105915909B (zh) 一种高动态范围图像分层压缩方法
TWI473039B (zh) 影像的動態範圍壓縮與局部對比增強方法及影像處理裝置
KR102523505B1 (ko) 역 톤 매핑을 위한 방법 및 장치
US8970746B2 (en) Image processing device, storage medium, and image processing method for correcting an image
US20100278423A1 (en) Methods and systems for contrast enhancement
US20160335750A1 (en) Adaptive contrast in image processing and display
JP2007310887A (ja) 画像データの自動マッピング方法及び画像処理デバイス
CN106570838A (zh) 一种图像亮度优化方法及装置
US20130329135A1 (en) Real time denoising of video
US8331695B1 (en) Integrated circuit having a circuit for and method of updating parameters associated with a background estimation portion of a video frame
WO2018100950A1 (fr) Dispositif de traitement d'image, caméra numérique, programme de traitement d'image et support d'enregistrement
CN112788322B (zh) 自适应白平衡处理方法、装置、介质及电子设备
CN114998122A (zh) 一种低照度图像增强方法
CN111476744A (zh) 一种基于分类及大气成像模型的水下图像增强方法
US8351724B2 (en) Blue sky color detection technique
US11082613B2 (en) Image adjusting method and image adjusting device
JP5327766B2 (ja) デジタル画像における記憶色の修正
WO2022246663A1 (fr) Procédé, dispositif et système de traitement d'image, et support d'enregistrement

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21942247

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE